Mining Users' Intentions from Thai Tweets Using BERT Models

Main Article Content

Nattapong Sanchan


In this paper, we explore the mining of users’ intentions in text. We viewed that being able to identify the intentions of users expressed in textual data provides us to specifically know aims and what users want to do. In the experiment, we collected tweets, constructed a Thai intention corpus, and performed a binary classification task on the corpus. We investigated the intent classification results derived through the application of 3 different Bidirectional Encoder Representations from Transformers (BERT), Word Embedding, and Bag of Words models. The results revealed that BERT Based EN-TH Cased model outperforms other models in both classification and processing time aspects. It achieves the F1 Score of 0.81 and performs the classification task faster than other BERT models up to 15%.

Article Details

How to Cite
N. Sanchan, “Mining Users’ Intentions from Thai Tweets Using BERT Models”, JIST, vol. 13, no. 1, pp. 17–25, Jun. 2023.
Research Article: Soft Computing (Detail in Scope of Journal)


Gupta, V. Pant, S. Kumar, & P. K. Bansal, “Bank Loan Prediction System using Machine Learning,” 2020 9th International Conference System Modeling and Advancement in Research Trends (SMART), 4, 12, 2020, pp. 423 – 426.

Schank RC, Abelson RP. Scripts, plans, goals, and understanding. Hillsdale, New Jersey: Lawrence Erlbaum Associates; 1997.

Mckevitt P, “Analysing coherence of intention in natural language dialogue,” Ph.D. thesis. Exeter: University of Exeter; 1991.

Hollerit, B., Kröll, M., & Strohmaier, M, “Towards linking buyers and sellers: detecting commercial intent on Twitter,” In Proceedings of the 22nd International Conference on World Wide Web. 2023, pp. 629-632.

Wang J, Cong G, Zhao XW, Li X, “Mining User Intents in Twitter: A Semi-Supervised Approach to Inferring Intent Categories for Tweets, ” The Twenty-Ninth AAAI Conference on Artificial Intelligence. ’05, 2015, pp.339-345.